Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/asimons81/hardproof/verifynpx skills add asimons81/hardproof --skill verifygit clone --depth 1 https://github.com/asimons81/hardproofWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00021 | $0.00292 |
| Opus 5 | $0.00010 | $0.00146 |
| Sonnet 5 | $0.00004 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Prove the Workspace State
Purpose
Tie completion claims to explicit successful checks executed against the current Git workspace snapshot.
When to use
Use for the VERIFY stage selected by the active run context.
Inputs
Use configured verification checks, profile requirements, current review outcome, Git state, and existing evidence records.
Procedure
- Inspect which required checks are configured and missing.
- Invoke
hardproof_verify; do not substitute an unrecorded terminal run. - Treat timeouts, malformed results, unknown exit status, or workspace changes during execution as non-passing.
- Inspect stored redacted output and address failures in IMPLEMENT.
- Rerun checks after every code change that makes evidence stale.
Required records
Quick and Standard require at least one fresh passing check; Critical requires at least two. Evidence must include an explicit zero exit code and matching workspace identity.
Exit criteria
All profile-required evidence is fresh, passing, and attributable to the final workspace state.
Failure modes
Never infer success from reassuring output, stale evidence, a missing exit code, or a prior commit. Return to IMPLEMENT for fixes and REVIEW when the diff changes materially.
Verification
Use hardproof_report to inspect evidence freshness, then call hardproof_transition for DELIVER.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 35 lines · 21 tokens per session scan A 43435c527255
verify is a skill published in the GitHub repository asimons81/hardproof (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 292 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
manuscript-typography
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic…
architecture-reviewer
Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports. Triggers on: "review architecture", "critique design", "audit system", "assess scalability", "enterprise readiness", "technical due diligence". NOT for diagrams, use…
concept-to-video
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition. Triggers on: "create a video", "animate this", "make an explainer", "manim animation", "motion graphic". NOT for React video, use remotion-video.
linkedin-post-style
Writes LinkedIn posts in a direct, analytical, dry-humored technical voice with visual companion guidance. Triggers on: "write this in my style", "draft a post", "rewrite this for LinkedIn", "post about this", "how should I phrase this".
manuscript-provenance
Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).
manuscript-review
Pre-publication manuscript audit producing a section-level refactoring report with citation hygiene and submission-readiness checks. Triggers on: "review my paper", "check before submission", "is this ready to submit", "pre-pub checklist", "refactor my paper", "check my references", "does the abstract work".